With the rapid development of smart devices, people's lives have become easier, especially for visually disabled or special-needs people. The new achievements in the fields of machine learning and deep learning let people identify and recognise the surrounding environment. In this study, the efficiency and high performance of deep learning architecture are used to build an image classification system in both indoor and outdoor environments. The proposed methodology starts with collecting two datasets (indoor and outdoor) from different separate datasets. In the second step, the collected dataset is split into training, validation, and test sets. The pre-trained GoogleNet and MobileNet-V2 models are trained using the indoor and outdoor sets, resulting in four trained models. The test sets are used to evaluate the trained models using many evaluation metrics (accuracy, TPR, FNR, PPR, FDR). Results of Google Net model indicate the high performance of the designed models with 99.34% and 99.76% accuracies for indoor and outdoor datasets, respectively. For Mobile Net models, the result accuracies are 99.27% and 99.68% for indoor and outdoor sets, respectively. The proposed methodology is compared with similar ones in the field of object recognition and image classification, and the comparative study proves the transcendence of the propsed system.
The extracted oil from the Chia seeds white and black were used in the manufacture of certain foods such as mayonnaise. The results of the sensory evaluation showed that the product was acceptable except for the flavor of white chia seed oil. The seeds were fully used in the manufacture of the nutella. The results of the sensory evaluation were encouraging the use of the extracted oil from the black chia seeds in the production of the nutella except the spread property. Chia seeds were also used in the manufacture of pudding. The results of the sensory evaluation showed an excellent and acceptable product of black chia seeds oil can be obtained, while the white seeds did not receive the acceptance in terms of color and flavor.
A novel encapsulated deep eutectic solvent (DES) was introduced for biodiesel production via a two-step process. The DES was encapsulated in medical capsules and were used to reduce the free fatty acid (FFA) content of acidic crude palm oil (ACPO) to the minimum acceptable level (< 1%). The DES was synthesized from methyltriphenylphosphonium bromide (MTPB) and p-toluenesulfonic acid (PTSA). The effects pertaining to different operating conditions such as capsule dosage, reaction time, molar ratio, and reaction temperature were optimized. The FFA content of ACPO was reduced from existing 9.61% to less than 1% under optimum operating conditions. This indicated that encapsulated MTPB-DES performed high catalytic activity in FFA esterificatio
... Show MoreThe Braille Recognition System is the process of capturing a Braille document image and turning its content into its equivalent natural language characters. The Braille Recognition System's cell transcription and Braille cell recognition are the two basic phases that follow one another. The Braille Recognition System is a technique for locating and recognizing a Braille document stored as an image, such as a jpeg, jpg, tiff, or gif image, and converting the text into a machine-readable format, such as a text file. BCR translates an image's pixel representation into its character representation. As workers at visually impaired schools and institutes, we profit from Braille recognition in a variety of ways. The Braille Recognition S
... Show MoreMetal-organic frameworks (MOFs) have emerged as revolutionary materials for developing advanced biosensors, especially for detecting reactive oxygen species (ROS) and hydrogen peroxide (H₂O₂) in biomedical applications. This comprehensive review explores the current state-of-the-art in MOF-based biosensors, covering fundamental principles, design strategies, performance features, and clinical uses. MOFs offer unique benefits, including exceptional porosity (up to 10,400 m²/g), tunable structures, biocompatibility, and natural enzyme-mimicking properties, making them ideal platforms for sensitive and selective detection of ROS and H₂O₂. Recent advances have shown significant improvements in detection capabilities, with limit
... Show MoreImage compression is a serious issue in computer storage and transmission, that simply makes efficient use of redundancy embedded within an image itself; in addition, it may exploit human vision or perception limitations to reduce the imperceivable information Polynomial coding is a modern image compression technique based on modelling concept to remove the spatial redundancy embedded within the image effectively that composed of two parts, the mathematical model and the residual. In this paper, two stages proposed technqies adopted, that starts by utilizing the lossy predictor model along with multiresolution base and thresholding techniques corresponding to first stage. Latter by incorporating the near lossless com
... Show MoreThis research aims to:
1 – Make a proposed module for (aesthetics) for the second stage - Department of Art Education under education theories.
2 - Verification from the effect of the proposed module on student achievement and motivation towards learning aesthetics material.
To verification the second goal we wording these two hypotheses:
1- There are no individual differences with statistically significant at level (0.05) between the student's scores average. (Experimental group ) who studied according to the proposed module and the average student's scores (control group) who studied in the usual way for the achievement test for the Aesthetics material.
2- There are no individual differences with statistically signifi
In this article, Convolution Neural Network (CNN) is used to detect damage and no damage images form satellite imagery using different classifiers. These classifiers are well-known models that are used with CNN to detect and classify images using a specific dataset. The dataset used belongs to the Huston hurricane that caused several damages in the nearby areas. In addition, a transfer learning property is used to store the knowledge (weights) and reuse it in the next task. Moreover, each applied classifier is used to detect the images from the dataset after it is split into training, testing and validation. Keras library is used to apply the CNN algorithm with each selected classifier to detect the images. Furthermore, the performa
... Show MoreClassifying an overlapping object is one of the main challenges faced by researchers who work in object detection and recognition. Most of the available algorithms that have been developed are only able to classify or recognize objects which are either individually separated from each other or a single object in a scene(s), but not overlapping kitchen utensil objects. In this project, Faster R-CNN and YOLOv5 algorithms were proposed to detect and classify an overlapping object in a kitchen area. The YOLOv5 and Faster R-CNN were applied to overlapping objects where the filter or kernel that are expected to be able to separate the overlapping object in the dedicated layer of applying models. A kitchen utensil benchmark image database and
... Show More